学术报告
A Mini-Batch Proximal Stochastic Recursive Gradient Algorithm with Diagonal Barzilai–Borwein Stepsize
于腾腾（北京农学院）
报告时间：2023年9月9日星期六 15：15-16：00
报告地点：沙河主楼E405
报告摘要: Many machine learning problems can be formulated as minimizing the sum of a function and a non-smooth regularization term. Proximal stochastic gradient methods are popular for solving such composite optimization problems. We propose a mini-batch proximal stochastic recursive gradient algorithm SRG-DBB, which incorporates the diagonal Barzilai–Borwein (DBB) stepsize strategy to capture the local geometry of the problem. The linear convergence and complexity of SRG-DBB are analyzed for strongly convex functions. We further establish the linear convergence of SRG-DBB under the non-strong convexity condition. Moreover, it is proved that SRG-DBB converges sublinearly in the convex case. Numerical experiments on standard data sets indicate that the performance of SRG-DBB is better than or comparable to the proximal stochastic recursive gradient algorithm with best-tuned scalar stepsizes or BB stepsizes. Furthermore, SRG-DBB is superior to some advanced mini-batch proximal stochastic gradient methods.
报告人简介：于腾腾，2016年硕士毕业于西安电子科技大学，师从刘三阳教授。2021年博士毕业于河北工业大学，师从刘新为教授。2021年10月至2023年8月在中国科学院数学与系统科学研究院从事博士后研究，合作导师袁亚湘院士。主要研究兴趣为大规模机器学习中的随机梯度算法，相关成果发表在IEEE Transactions on Neural Networks and Learning Systems、Journal of Scientific Computing、Journal of the Operations Research Society of China等期刊。
邀请人：崔春风
